{ "data_id": "33175", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5767", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5767", "version": 9, "version_label": null, "description": "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL5767 (TID: 101546), and it has 101 rows and 64 features (not including molecule IDs and class feature: molecule_id and pXC50). The features represent Molecular Descriptors which were generated from SMILES strings. Missing value imputation was applied to this dataset (By choosing the Median). Feature selection was also applied.", "format": "ARFF", "uploader": "Noureddin Sadawi", "uploader_id": 62, "visibility": "public", "creator": "\"Dr Jeremy Besnard, Dr Ivan Olier, Dr Noureddin Sadawi, Dr Larisa Soldatova, Dr Crina Grosan, Prof Ross King, Dr Richard Bickerton, Prof Andrew Hopkins and Dr Willem van Hoorn\"", "contributor": null, "date": "2016-07-15 12:06:28", "update_comment": null, "last_update": "2016-07-15 12:06:28", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3498939\/data_52707.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5767", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL5767 (TID: 101546), and it has 101 rows and 64 features (not including molecule IDs and class feature: molecule_id and pXC50). The features represent Molecular Descriptors which were generated from SMILES strings. Missing value imputation was applied to this dataset (By choosing the Median). Feature selection was also applied. " ], "weight": 5 }, "qualities": { "NumberOfInstances": 101, "NumberOfFeatures": 66, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 65, "NumberOfSymbolicFeatures": 1, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.6534653465346535, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 0.7344235212345542, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": -0.14318646324238068, "Quartile2MeansOfNumericAtts": 4.19341584158416, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 4.957898842740766, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": -0.15787069960862551, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -2.0404040404040384, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.5813947041212179, "MaxKurtosisOfNumericAtts": 6.909091397259546, "MinMeansOfNumericAtts": -3.4143564356435645, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 187.22939603960396, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 1.8779455295260177, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.48484848484848, "Quartile3MeansOfNumericAtts": 7.20840099009901, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.755353223837176, "PercentageOfSymbolicFeatures": 1.5151515151515151, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 2.688244885371821, "MinStdDevOfNumericAtts": 0.056669589518873555, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.3240220121261736, "MaxStdDevOfNumericAtts": 64.82481396719612, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.14840534280812578, "Quartile3StdDevOfNumericAtts": 2.4731732313398345, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.9744603960396039, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 1.027532538324913, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 14.211136329017517, "Quartile1SkewnessOfNumericAtts": -0.9157264894777497, "AutoCorrelation": 0.20920999999999992, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.3619197719173141 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "65", "type": "numeric", "distinct": "96", "missing": "0", "target": "1", "min": "4", "max": "9", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "101", "missing": "0", "identifier": "1", "distr": [] }, { "name": "GGI9", "index": "1", "type": "numeric", "distinct": "54", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SpDiam_AEA.bo.", "index": "2", "type": "numeric", "distinct": "63", "missing": "0", "min": "4", "max": "6", "mean": "6", "stdev": "0" }, { "name": "ZM1Mad", "index": "3", "type": "numeric", "distinct": "83", "missing": "0", "min": "32", "max": "319", "mean": "169", "stdev": "57" }, { "name": "SsOH", "index": "4", "type": "numeric", "distinct": "31", "missing": "0", "min": "0", "max": "30", "mean": "4", "stdev": "7" }, { "name": "X3v", "index": "5", "type": "numeric", "distinct": "98", "missing": "0", "min": "1", "max": "8", "mean": "4", "stdev": "2" }, { "name": "NsOH", "index": "6", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "1" }, { "name": "SpMax2_Bh.m.", "index": "7", "type": "numeric", "distinct": "84", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "X4v", "index": "8", "type": "numeric", "distinct": "96", "missing": "0", "min": "0", "max": "7", "mean": "3", "stdev": "1" }, { "name": "SpMax4_Bh.m.", "index": "9", "type": "numeric", "distinct": "84", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "ATS1m", "index": "10", "type": "numeric", "distinct": "79", "missing": "0", "min": "2", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SM03_EA.bo.", "index": "11", "type": "numeric", "distinct": "40", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "1" }, { "name": "ZM2Mad", "index": "12", "type": "numeric", "distinct": "90", "missing": "0", "min": "33", "max": "372", "mean": "187", "stdev": "65" }, { "name": "SpMax3_Bh.m.", "index": "13", "type": "numeric", "distinct": "87", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "nArOH", "index": "14", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "O.057", "index": "15", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "SM04_EA.bo.", "index": "16", "type": "numeric", "distinct": "75", "missing": "0", "min": "6", "max": "8", "mean": "7", "stdev": "0" }, { "name": "ATS2s", "index": "17", "type": "numeric", "distinct": "89", "missing": "0", "min": "4", "max": "7", "mean": "6", "stdev": "0" }, { "name": "X2v", "index": "18", "type": "numeric", "distinct": "98", "missing": "0", "min": "1", "max": "11", "mean": "7", "stdev": "2" }, { "name": "ATS2m", "index": "19", "type": "numeric", "distinct": "81", "missing": "0", "min": "2", "max": "4", "mean": "4", "stdev": "0" }, { "name": "X2sol", "index": "20", "type": "numeric", "distinct": "84", "missing": "0", "min": "3", "max": "22", "mean": "12", "stdev": "3" }, { "name": "CATS2D_04_DL", "index": "21", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "10", "mean": "4", "stdev": "3" }, { "name": "SpMax1_Bh.i.", "index": "22", "type": "numeric", "distinct": "56", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpMax1_Bh.v.", "index": "23", "type": "numeric", "distinct": "53", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "GATS1s", "index": "24", "type": "numeric", "distinct": "79", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "X1v", "index": "25", "type": "numeric", "distinct": "90", "missing": "0", "min": "2", "max": "14", "mean": "8", "stdev": "2" }, { "name": "X5v", "index": "26", "type": "numeric", "distinct": "99", "missing": "0", "min": "0", "max": "6", "mean": "2", "stdev": "1" }, { "name": "X4sol", "index": "27", "type": "numeric", "distinct": "84", "missing": "0", "min": "1", "max": "12", "mean": "7", "stdev": "3" }, { "name": "SpMax1_Bh.p.", "index": "28", "type": "numeric", "distinct": "51", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "XMOD", "index": "29", "type": "numeric", "distinct": "90", "missing": "0", "min": "21", "max": "129", "mean": "76", "stdev": "21" }, { "name": "SpMax1_Bh.e.", "index": "30", "type": "numeric", "distinct": "53", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpDiam_AEA.ri.", "index": "31", "type": "numeric", "distinct": "69", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "CATS2D_02_AP", "index": "32", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "1" }, { "name": "N.069", "index": "33", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "P_VSA_i_1", "index": "34", "type": "numeric", "distinct": "12", "missing": "0", "min": "0", "max": "63", "mean": "8", "stdev": "12" }, { "name": "P_VSA_s_1", "index": "35", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "12", "mean": "5", "stdev": "3" }, { "name": "CATS2D_06_DD", "index": "36", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "1" }, { "name": "CATS2D_06_DP", "index": "37", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "SpMax3_Bh.i.", "index": "38", "type": "numeric", "distinct": "77", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "ATSC8e", "index": "39", "type": "numeric", "distinct": "95", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "nN", "index": "40", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "3", "stdev": "1" }, { "name": "PDI", "index": "41", "type": "numeric", "distinct": "69", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "P_VSA_e_3", "index": "42", "type": "numeric", "distinct": "26", "missing": "0", "min": "0", "max": "116", "mean": "58", "stdev": "29" }, { "name": "P_VSA_i_4", "index": "43", "type": "numeric", "distinct": "30", "missing": "0", "min": "0", "max": "157", "mean": "60", "stdev": "32" }, { "name": "SM06_AEA.ed.", "index": "44", "type": "numeric", "distinct": "77", "missing": "0", "min": "10", "max": "13", "mean": "12", "stdev": "1" }, { "name": "SM05_EA.bo.", "index": "45", "type": "numeric", "distinct": "68", "missing": "0", "min": "5", "max": "9", "mean": "8", "stdev": "1" }, { "name": "P_VSA_s_3", "index": "46", "type": "numeric", "distinct": "74", "missing": "0", "min": "0", "max": "74", "mean": "22", "stdev": "14" }, { "name": "IAC", "index": "47", "type": "numeric", "distinct": "78", "missing": "0", "min": "17", "max": "107", "mean": "67", "stdev": "19" }, { "name": "TIC0", "index": "48", "type": "numeric", "distinct": "78", "missing": "0", "min": "17", "max": "107", "mean": "67", "stdev": "19" }, { "name": "X3sol", "index": "49", "type": "numeric", "distinct": "84", "missing": "0", "min": "2", "max": "14", "mean": "8", "stdev": "3" }, { "name": "N.", "index": "50", "type": "numeric", "distinct": "42", "missing": "0", "min": "0", "max": "21", "mean": "7", "stdev": "4" }, { "name": "SpMin1_Bh.i.", "index": "51", "type": "numeric", "distinct": "43", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "GGI6", "index": "52", "type": "numeric", "distinct": "57", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "MATS1e", "index": "53", "type": "numeric", "distinct": "78", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Eig01_AEA.dm.", "index": "54", "type": "numeric", "distinct": "30", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "1" }, { "name": "MAXDN", "index": "55", "type": "numeric", "distinct": "95", "missing": "0", "min": "1", "max": "6", "mean": "4", "stdev": "1" }, { "name": "NddssS", "index": "56", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "nS", "index": "57", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "S.110", "index": "58", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "SddssS", "index": "59", "type": "numeric", "distinct": "73", "missing": "0", "min": "-14", "max": "0", "mean": "-3", "stdev": "2" }, { "name": "SpDiam_AEA.dm.", "index": "60", "type": "numeric", "distinct": "30", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "1" }, { "name": "SpMax1_Bh.s.", "index": "61", "type": "numeric", "distinct": "18", "missing": "0", "min": "6", "max": "9", "mean": "8", "stdev": "0" }, { "name": "SpMax_AEA.dm.", "index": "62", "type": "numeric", "distinct": "30", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "1" }, { "name": "Eig01_EA.bo.", "index": "63", "type": "numeric", "distinct": "34", "missing": "0", "min": "3", "max": "5", "mean": "5", "stdev": "0" }, { "name": "nSO2N", "index": "64", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" } ], "nr_of_issues": 0, "nr_of_downvotes": 0, "nr_of_likes": 0, "nr_of_downloads": 0, "total_downloads": 0, "reach": 0, "reuse": 0, "impact_of_reuse": 0, "reach_of_reuse": 0, "impact": 0 }